Downloads · 30 days
4
13% of all-time downloads
Llama-3.2-3B-Instruct-nbits4-GSNone-Axis0-HQQ
brunopio/Llama-3.2-3B-Instruct-nbits4-GSNone-Axis0-HQQ
Llama-3.2-3B-Instruct-nbits4-GSNone-Axis0-HQQ is a machine learning model from brunopio. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a version of the Llama-3.2-3B-Instruct model quantized to 4-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqqblog/
All-time downloads
31
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.2 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024
- SHA
- f2999796
Base models
Model card
From the Hugging Face model README
This is a version of the Llama-3.2-3B-Instruct model quantized to 4-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/
To run the model, install the HQQ library from https://github.com/mobiusml/hqq and use it as follows:
model_id = 'brunopio/Llama-3.2-3B-Instruct-nbits4-GS64-Axis1-HQQ'
from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = HQQModelForCausalLM.from_quantized(model_id)
Limitations: <br> -Only supports single GPU runtime.<br> -Not compatible with HuggingFace's PEFT.<br>
- Type
- llama
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024